Skip to main content
Glama

generate_ipadapter

Create images influenced by 1–4 reference images using IP-Adapter style, composition, and content blending. Set reference weight and timing to control how strongly references shape the output.

Instructions

Generate image with IP-Adapter multi-reference style blending.

Feeds 1--4 reference images into the diffusion model to influence style, composition, and content of the generated output.

Args: prompt: Text prompt describing desired output reference_images: List of 1-4 image filenames from comfyui/input/ negative_prompt: What to avoid in the output negative_embedding: Textual inversion embedding name (e.g., "DeepNegative_xl_v1") to append to negative prompt width: Output width (512 recommended for 6GB VRAM) height: Output height steps: Sampling steps (10-20 for speed, 30+ for quality) cfg_scale: Classifier-free guidance scale sampler: Sampling algorithm scheduler: Noise schedule seed: Fixed seed for reproducibility (None = random) reference_weight: How strongly reference images influence output (0.0-1.0+) weight_type: "style transfer", "composition", "linear", etc. denoise: Denoising strength (1.0 = full generation) start_at: When to start applying IP-Adapter (0.0 = beginning) end_at: When to stop applying IP-Adapter (1.0 = end) embeds_scaling: Embedding scaling strategy loras: Optional list of LoRA configs [{"name": str, "weight": float}] output_format: Always "png" for now output_prefix: Filename prefix for saved images

Returns: Dict with job_id, status, queue_position

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>",
      "reference_images": "<reference_images>"
    },
    "name": "generate_ipadapter"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNo
lorasNo
stepsNo
widthNo
end_atNo
heightNo
promptYes
denoiseNo
samplerNodpmpp_2m
start_atNo
cfg_scaleNo
schedulerNokarras
weight_typeNostyle transfer
output_formatNopng
output_prefixNoipadapter
embeds_scalingNoV only
ipadapter_modelNo
negative_promptNotext, watermark, blurry, low quality
reference_imagesYes
reference_weightNo
clip_vision_modelNo
negative_embeddingNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It discloses the return shape (job_id, status, queue_position), which usefully signals asynchronous queueing, but says nothing about GPU cost, VRAM failure modes, whether jobs can be cancelled, or that results must be retrieved via get_job_status.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded summary followed by an Args/Returns block, so an agent can skim to the parameter it needs. It is long, but almost every line adds information; the 'always png for now' line is the only near-filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 22-parameter GPU generation tool with no annotations, the definition covers inputs and the return dict well, and the output schema is present so return values need no more detail. However, two schema parameters go undocumented and nothing explains the job lifecycle after submission, leaving a real gap for a tool this complex.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the docstring is the only parameter documentation and it does most of the job: it adds constraints absent from the schema (reference_images are 1-4 filenames from comfyui/input/, seed=None means random, weight_type values, reference_weight range, denoise=1.0 is full generation). Reward is capped because ipadapter_model and clip_vision_model appear in the schema but are never explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first two sentences state a specific verb and resource (generate an image) plus the distinguishing mechanism (IP-Adapter feeding 1-4 reference images to blend style, composition and content). That differentiates it in spirit from a plain generate_image, though it never names the sibling it is not.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the 1-4 reference-image scenario tells an agent when this fits, and width=512 is flagged for 6GB VRAM. There is no explicit when-not or pointer to generate_image / batch_generate_ipadapter when a single reference or batch run is wanted.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.